Chunked Attention-based Encoder-Decoder Model for Streaming Speech Recognition
Zeineldeen, Mohammad, Zeyer, Albert, Schlüter, Ralf, Ney, Hermann
We study a streamable attention-based encoder-decoder model in which either the decoder, or both the encoder and decoder, operate on pre-defined, fixed-size windows called chunks. A special end-of-chunk (EOC) symbol advances from one chunk to the next chunk, effectively replacing the conventional end-of-sequence symbol. This modification, while minor, situates our model as equivalent to a transducer model that operates on chunks instead of frames, where EOC corresponds to the blank symbol. We further explore the remaining differences between a standard transducer and our model. Additionally, we examine relevant aspects such as long-form speech generalization, beam size, and length normalization. Through experiments on Librispeech and TED-LIUM-v2, and by concatenating consecutive sequences for long-form trials, we find that our streamable model maintains competitive performance compared to the non-streamable variant and generalizes very well to long-form speech.
Sep-15-2023
- Country:
- Europe > Germany (0.04)
- Oceania > Australia
- North America > United States
- New York > New York County
- New York City (0.04)
- California > San Francisco County
- San Francisco (0.14)
- New York > New York County
- Asia
- Genre:
- Research Report (0.40)
- Technology: